lynxkite / examples /Cheminformatics /Example workspace.lynxkite.json
abhik1368's picture
Update Cheminformatrics use Cases (#155)
9d40ea2 unverified
{
"edges": [
{
"id": "Import CSV 1 Draw molecules 1",
"source": "Import CSV 1",
"sourceHandle": "output",
"target": "Draw molecules 1",
"targetHandle": "df"
},
{
"id": "Draw molecules 1 View tables 1",
"source": "Draw molecules 1",
"sourceHandle": "output",
"target": "View tables 1",
"targetHandle": "bundle"
},
{
"id": "Import file 1 View mol filter 1",
"source": "Import file 1",
"sourceHandle": "output",
"target": "View mol filter 1",
"targetHandle": "bundle"
},
{
"id": "Draw molecules 2 View tables 2",
"source": "Draw molecules 2",
"sourceHandle": "output",
"target": "View tables 2",
"targetHandle": "bundle"
},
{
"id": "Import file 1 Train QSAR model 1",
"source": "Import file 1",
"sourceHandle": "output",
"target": "Train QSAR model 1",
"targetHandle": "bundle"
},
{
"id": "Train QSAR model 1 View tables 3",
"source": "Train QSAR model 1",
"sourceHandle": "output",
"target": "View tables 3",
"targetHandle": "bundle"
},
{
"id": "Import file 1 Lipinski filter 1",
"source": "Import file 1",
"sourceHandle": "output",
"target": "Lipinski filter 1",
"targetHandle": "bundle"
},
{
"id": "Lipinski filter 1 Draw molecules 2",
"source": "Lipinski filter 1",
"sourceHandle": "output",
"target": "Draw molecules 2",
"targetHandle": "df"
},
{
"id": "Import file 1 View mol image 1",
"source": "Import file 1",
"sourceHandle": "output",
"target": "View mol image 1",
"targetHandle": "bundle"
}
],
"env": "LynxKite Graph Analytics",
"nodes": [
{
"data": {
"__execution_delay": 0.0,
"collapsed": false,
"display": null,
"error": null,
"input_metadata": [],
"meta": {
"color": "orange",
"inputs": [],
"name": "Import CSV",
"outputs": [
{
"name": "output",
"position": "right",
"type": {
"type": "None"
}
}
],
"params": [
{
"default": null,
"name": "filename",
"type": {
"type": "<class 'str'>"
}
},
{
"default": "<from file>",
"name": "columns",
"type": {
"type": "<class 'str'>"
}
},
{
"default": "<auto>",
"name": "separator",
"type": {
"type": "<class 'str'>"
}
}
],
"type": "basic"
},
"params": {
"columns": "<from file>",
"filename": "uploads/CHEMBL313_sel.csv",
"separator": "<auto>"
},
"status": "done",
"title": "Import CSV"
},
"dragHandle": ".bg-primary",
"height": 206.0,
"id": "Import CSV 1",
"position": {
"x": -1645.1133255451734,
"y": -601.1570975227908
},
"type": "basic",
"width": 314.0
},
{
"data": {
"__execution_delay": null,
"collapsed": false,
"error": null,
"input_metadata": [
{
"dataframes": {
"df": {
"columns": [
"Name",
"SMILES",
"image",
"pIC50"
]
}
},
"other": {},
"relations": []
}
],
"meta": {
"color": "orange",
"inputs": [
{
"name": "bundle",
"position": "left",
"type": {
"type": "<class 'lynxkite_graph_analytics.core.Bundle'>"
}
}
],
"name": "View tables",
"outputs": [],
"params": [
{
"default": 100,
"name": "limit",
"type": {
"type": "<class 'int'>"
}
}
],
"type": "table_view"
},
"params": {},
"status": "done",
"title": "View tables"
},
"dragHandle": ".bg-primary",
"height": 296.0,
"id": "View tables 1",
"position": {
"x": -870.3210345250492,
"y": -671.6118451917321
},
"type": "table_view",
"width": 682.0
},
{
"data": {
"__execution_delay": 0.0,
"collapsed": null,
"display": null,
"error": null,
"input_metadata": [],
"meta": {
"color": "orange",
"inputs": [],
"name": "Import file",
"outputs": [
{
"name": "output",
"position": "right",
"type": {
"type": "None"
}
}
],
"params": [
{
"default": null,
"name": "file_path",
"type": {
"type": "<class 'str'>"
}
},
{
"default": null,
"name": "table_name",
"type": {
"type": "<class 'str'>"
}
},
{
"default": null,
"name": "file_format",
"type": {
"enum": [
"csv",
"parquet",
"json",
"excel"
]
}
},
{
"default": "csv",
"groups": {
"csv": [
{
"default": "<from file>",
"name": "columns",
"type": {
"type": "<class 'str'>"
}
},
{
"default": "<auto>",
"name": "separator",
"type": {
"type": "<class 'str'>"
}
}
],
"excel": [
{
"default": "Sheet1",
"name": "sheet_name",
"type": {
"type": "<class 'str'>"
}
}
],
"json": [],
"parquet": []
},
"name": "file_format_group",
"selector": {
"default": "csv",
"name": "file_format",
"type": {
"enum": [
"csv",
"parquet",
"json",
"excel"
]
}
},
"type": "group"
}
],
"type": "basic"
},
"params": {
"columns": "<from file>",
"file_format": "csv",
"file_format_group": "csv",
"file_path": "uploads/CHEMBL313_sel.csv",
"table_name": "data"
},
"status": "done",
"title": "Import file"
},
"dragHandle": ".bg-primary",
"height": 331.0,
"id": "Import file 1",
"position": {
"x": -1690.536661950572,
"y": -192.47882875357882
},
"type": "basic",
"width": 326.0
},
{
"data": {
"__execution_delay": 0.0,
"collapsed": null,
"display": null,
"error": null,
"input_metadata": [
{}
],
"meta": {
"color": "orange",
"inputs": [
{
"name": "df",
"position": "left",
"type": {
"type": "<class 'pandas.core.frame.DataFrame'>"
}
}
],
"name": "Draw molecules",
"outputs": [
{
"name": "output",
"position": "right",
"type": {
"type": "None"
}
}
],
"params": [
{
"default": null,
"name": "smiles_column",
"type": {
"type": "<class 'str'>"
}
},
{
"default": "image",
"name": "image_column",
"type": {
"type": "<class 'str'>"
}
}
],
"type": "basic"
},
"params": {
"image_column": "image",
"smiles_column": "SMILES"
},
"status": "done",
"title": "Draw molecules"
},
"dragHandle": ".bg-primary",
"height": 225.0,
"id": "Draw molecules 1",
"position": {
"x": -1168.2624512141447,
"y": -616.8610881973451
},
"type": "basic",
"width": 234.0
},
{
"data": {
"__execution_delay": 0.0,
"collapsed": null,
"error": null,
"input_metadata": [
{
"dataframes": {
"data": {
"columns": [
"Name",
"SMILES",
"mol",
"pIC50"
]
}
},
"other": {},
"relations": []
}
],
"meta": {
"color": "orange",
"inputs": [
{
"name": "bundle",
"position": "left",
"type": {
"type": "<class 'inspect._empty'>"
}
}
],
"name": "View mol filter",
"outputs": [],
"params": [
{
"default": null,
"name": "table_name",
"type": {
"type": "<class 'str'>"
}
},
{
"default": null,
"name": "SMILES_Column",
"type": {
"type": "<class 'str'>"
}
},
{
"default": null,
"name": "mols_per_row",
"type": {
"type": "<class 'int'>"
}
},
{
"default": null,
"name": "filter_smarts",
"type": {
"type": "<class 'str'>"
}
},
{
"default": null,
"name": "filter_smiles",
"type": {
"type": "<class 'str'>"
}
},
{
"default": true,
"name": "highlight",
"type": {
"type": "<class 'bool'>"
}
}
],
"type": "image"
},
"params": {
"SMILES_Column": "SMILES",
"filter_smarts": "",
"filter_smiles": "CN1C2CC(CC1CC2)c1ccccc1",
"highlight": true,
"mols_per_row": "4",
"table_name": "data"
},
"status": "done",
"title": "View mol filter"
},
"dragHandle": ".bg-primary",
"height": 229.0,
"id": "View mol filter 1",
"position": {
"x": -796.5179679488858,
"y": -20.974048336481403
},
"type": "image",
"width": 416.0
},
{
"data": {
"__execution_delay": 0.0,
"collapsed": null,
"display": null,
"error": null,
"input_metadata": [
{}
],
"meta": {
"color": "orange",
"inputs": [
{
"name": "df",
"position": "left",
"type": {
"type": "<class 'pandas.core.frame.DataFrame'>"
}
}
],
"name": "Draw molecules",
"outputs": [
{
"name": "output",
"position": "right",
"type": {
"type": "None"
}
}
],
"params": [
{
"default": null,
"name": "smiles_column",
"type": {
"type": "<class 'str'>"
}
},
{
"default": "image",
"name": "image_column",
"type": {
"type": "<class 'str'>"
}
}
],
"type": "basic"
},
"params": {
"image_column": "image",
"smiles_column": "SMILES"
},
"status": "done",
"title": "Draw molecules"
},
"dragHandle": ".bg-primary",
"height": 184.0,
"id": "Draw molecules 2",
"position": {
"x": -280.6043043496203,
"y": 151.45994649399827
},
"type": "basic",
"width": 234.0
},
{
"data": {
"error": null,
"input_metadata": [
{
"dataframes": {
"df": {
"columns": [
"HBA",
"HBD",
"MW",
"Name",
"SMILES",
"image",
"logP",
"pIC50",
"pass_lipinski"
]
}
},
"other": {},
"relations": []
}
],
"meta": {
"color": "orange",
"inputs": [
{
"name": "bundle",
"position": "left",
"type": {
"type": "<class 'lynxkite_graph_analytics.core.Bundle'>"
}
}
],
"name": "View tables",
"outputs": [],
"params": [
{
"default": 100,
"name": "limit",
"type": {
"type": "<class 'int'>"
}
}
],
"type": "table_view"
},
"params": {
"limit": 100.0
},
"status": "done",
"title": "View tables"
},
"dragHandle": ".bg-primary",
"height": 429.0,
"id": "View tables 2",
"position": {
"x": 50.96521878343134,
"y": 102.82896600710055
},
"type": "table_view",
"width": 821.0
},
{
"data": {
"__execution_delay": 0.0,
"collapsed": null,
"display": null,
"error": null,
"input_metadata": [
{
"dataframes": {
"data": {
"columns": [
"Name",
"SMILES",
"pIC50"
]
}
},
"other": {},
"relations": []
}
],
"meta": {
"color": "orange",
"inputs": [
{
"name": "bundle",
"position": "left",
"type": {
"type": "<class 'inspect._empty'>"
}
}
],
"name": "Train QSAR model",
"outputs": [
{
"name": "output",
"position": "right",
"type": {
"type": "None"
}
}
],
"params": [
{
"default": null,
"name": "table_name",
"type": {
"type": "<class 'str'>"
}
},
{
"default": null,
"name": "smiles_col",
"type": {
"type": "<class 'str'>"
}
},
{
"default": null,
"name": "target_col",
"type": {
"type": "<class 'str'>"
}
},
{
"default": null,
"name": "fp_type",
"type": {
"type": "<class 'str'>"
}
},
{
"default": 2,
"name": "radius",
"type": {
"type": "<class 'int'>"
}
},
{
"default": 2048,
"name": "n_bits",
"type": {
"type": "<class 'int'>"
}
},
{
"default": 0.2,
"name": "test_size",
"type": {
"type": "<class 'float'>"
}
},
{
"default": 42,
"name": "random_state",
"type": {
"type": "<class 'int'>"
}
},
{
"default": "Models",
"name": "out_dir",
"type": {
"type": "<class 'str'>"
}
}
],
"type": "basic"
},
"params": {
"fp_type": "ecfp",
"n_bits": 2048.0,
"out_dir": "Models",
"radius": 2.0,
"random_state": 42.0,
"smiles_col": "SMILES",
"table_name": "data",
"target_col": "pIC50",
"test_size": 0.2
},
"status": "done",
"title": "Train QSAR model"
},
"dragHandle": ".bg-primary",
"height": 288.0,
"id": "Train QSAR model 1",
"position": {
"x": -1159.342067985799,
"y": -309.43299496669476
},
"type": "basic",
"width": 329.0
},
{
"data": {
"display": {
"dataframes": {
"df": {
"columns": [
"split",
"R2",
"MAE",
"RMSE"
],
"data": [
[
"train",
0.9417380311136551,
0.24223013565891363,
0.3009354647304392
],
[
"test",
0.27586659127848734,
0.8443154545454546,
1.098891477150744
]
]
}
},
"other": {},
"relations": []
},
"error": null,
"input_metadata": [
{
"dataframes": {
"df": {
"columns": [
"MAE",
"R2",
"RMSE",
"split"
]
}
},
"other": {},
"relations": []
}
],
"meta": {
"color": "orange",
"inputs": [
{
"name": "bundle",
"position": "left",
"type": {
"type": "<class 'lynxkite_graph_analytics.core.Bundle'>"
}
}
],
"name": "View tables",
"outputs": [],
"params": [
{
"default": 100,
"name": "limit",
"type": {
"type": "<class 'int'>"
}
}
],
"type": "table_view"
},
"params": {
"limit": 100.0
},
"status": "done",
"title": "View tables"
},
"dragHandle": ".bg-primary",
"height": 291.0,
"id": "View tables 3",
"position": {
"x": -757.0926975107354,
"y": -321.469271323077
},
"type": "table_view",
"width": 496.0
},
{
"data": {
"__execution_delay": 0.0,
"collapsed": null,
"display": null,
"error": null,
"input_metadata": [
{
"dataframes": {
"data": {
"columns": [
"Name",
"SMILES",
"mol",
"pIC50"
]
}
},
"other": {},
"relations": []
}
],
"meta": {
"color": "orange",
"inputs": [
{
"name": "bundle",
"position": "left",
"type": {
"type": "<class 'inspect._empty'>"
}
}
],
"name": "Lipinski filter",
"outputs": [
{
"name": "output",
"position": "right",
"type": {
"type": "None"
}
}
],
"params": [
{
"default": null,
"name": "table_name",
"type": {
"type": "<class 'str'>"
}
},
{
"default": null,
"name": "column_name",
"type": {
"type": "<class 'str'>"
}
},
{
"default": true,
"name": "strict_lipinski",
"type": {
"type": "<class 'bool'>"
}
}
],
"type": "basic"
},
"params": {
"column_name": "SMILES",
"strict_lipinski": true,
"table_name": "data"
},
"status": "done",
"title": "Lipinski filter"
},
"dragHandle": ".bg-primary",
"height": 299.0,
"id": "Lipinski filter 1",
"position": {
"x": -720.0507400376052,
"y": 276.1650594718383
},
"type": "basic",
"width": 402.0
},
{
"data": {
"__execution_delay": 0.0,
"collapsed": null,
"error": null,
"input_metadata": [
{
"dataframes": {
"data": {
"columns": [
"Name",
"SMILES",
"mol",
"pIC50"
]
}
},
"other": {},
"relations": []
}
],
"meta": {
"color": "orange",
"inputs": [
{
"name": "bundle",
"position": "left",
"type": {
"type": "<class 'inspect._empty'>"
}
}
],
"name": "View mol image",
"outputs": [],
"params": [
{
"default": null,
"name": "table_name",
"type": {
"type": "<class 'str'>"
}
},
{
"default": null,
"name": "smiles_column",
"type": {
"type": "<class 'str'>"
}
},
{
"default": null,
"name": "mols_per_row",
"type": {
"type": "<class 'int'>"
}
}
],
"type": "image"
},
"params": {
"mols_per_row": "4",
"smiles_column": "SMILES",
"table_name": "data"
},
"status": "done",
"title": "View mol image"
},
"dragHandle": ".bg-primary",
"height": 309.0,
"id": "View mol image 1",
"position": {
"x": -1378.339896172849,
"y": 280.2327514185724
},
"type": "image",
"width": 363.0
}
]
}